# US 2019/0317955 A1 · Determining missing content in a database

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0317955 A1
- Document ID: US20190317955A1
- Status: Published application
- Kind: A1
- Application number: 16/389,877
- Filed: 2019-04-19
- Published: 2019-10-17
- Earliest claimed: 2017-10-27
- Assignees: Babylon Partners Limited
- Applicants: Babylon Partners Limited
- Inventors: Vitalii ZHELEZNIAK; Daniel William BUSBRIDGE; April Tuesday SHEN; Samuel Laurence SMITH; Nils HAMMERLA
- Web page: https://patentgrep.com/patent/US20190317955A1

## CPC

- G06F 16/3344: {using natural language analysis}
- G06F 16/3347: {using vector based model}
- G06F 16/338: Presentation of query results
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 40/35: Discourse or dialogue representation
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/08: Learning methods
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Computer-implemented methods for determining missing content in a database are provided. The database may contain a plurality of known embedded sentences and their relationship to content. In one aspect, a method includes receiving new queries and generating new embedded sentences from said new queries. The method also includes determining whether the new embedded sentences are similar to known embedded sentences. The method also includes generating a message indicating that new embedded sentence is not linked to content. Systems are also provided.

## Claims

### Claim 1

A computer-implemented method for determining missing content in a database, said database containing a plurality of known embedded sentences and their relationship to content, the method comprising:
receiving new queries;
generating new embedded sentences from said new queries;
determining whether the new embedded sentences are similar to known embedded sentences; and
generating a message indicating that new embedded sentence is not linked to content.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, wherein the embedded sentences are clustered and a message is generated to indicate that more content is required if a cluster of new embedded sentences exceeds a predetermined size.

### Claim 3 (depends on 1)

The computer-implemented method according to claim 1, wherein an embedded sentence is generated from a new query using a decoding function and an encoding function, wherein in said encoding function, words contained in said query are mapped to a sentence vector and wherein in the decoding function, the context of the query is predicted using the sentence vector.

### Claim 4 (depends on 3)

The computer-implemented method according to claim 3, wherein a similarity between an embedded sentence derived from the new query and the embedded sentences in the database are determined in the embedded sentence space as defined by the output space of the decoder.

### Claim 5 (depends on 3)

The computer-implemented method according to claim 3, wherein a similarity between an embedded sentence derived from the new query and the embedded sentences in the database are determined in the embedded sentence space as defined by the output space of the encoder.

### Claim 6 (depends on 3)

The computer-implemented method according to claim 3, wherein in the decoding function, comprises at least three decoders, with one decoder for the natural language query and the other two decoders for the neighbouring sentences.

### Claim 7 (depends on 1)

The computer-implemented method according to claim 1, wherein the database contains medical information.

### Claim 8

A non-transitory computer-readable carrier medium comprising computer readable code configured to cause a computer to perform a computer-implemented method for determining missing content in a database, said database containing a plurality of known embedded sentences and their relationship to content, the method comprising:
receiving new queries;
generating new embedded sentences from said new queries;
determining whether the new embedded sentences are similar to known embedded sentences; and
generating a message indicating that new embedded sentence is not linked to content.

### Claim 9

A system for determining missing content in a database,
the system comprising:
a database containing a plurality of known embedded sentences and their relationship to content,
a user interface adapted to receive user inputted queries; and
a processor, the processor being adapted to:
generate new embedded sentences from said new queries;
determine whether the new embedded sentences are similar to known embedded sentences; and
generate a message indicating that new embedded sentence is not linked to content.

### Claim 10 (depends on 9)

The system according to claim 9, wherein the embedded sentences are clustered and a message is generated to indicate that more content is required if a cluster of new embedded sentences exceeds a predetermined size.
